Concepts

Base models

3 min readbeginnerUpdated 28 Sept 2026
1 · In one line

A base language model is a pretrained model before further instruction or conversational fine-tuning.

1 · What it is

A base language model is a pretrained model before further instruction or conversational fine-tuning.

A pretrained base version can complete text directly. It can also receive further instruction tuning. A parameter-efficient adapter still needs the base model that was fine-tuned.

Llama 2 includes both pretrained and fine-tuned models. Llama 2-Chat is optimized for dialogue use cases. Base models are not ideal for tasks that require following instructions.

2 · Why it exists

Model documentation distinguishes pretrained base versions from instruction-tuned variants.

Same familyModel families can publish both pretrained and instruction-tuned variants.
Different behaviorBase models suit text completion but are not ideal for tasks that require following instructions.
Adapter dependencyA parameter-efficient adapter still needs the base model that was fine-tuned.
3 · How it works

Trace one pretrained base model into direct completion or further tuning.

A pretrained base version can complete text directly or receive further instruction tuning.
  1. 1 · loadStart with the pretrained base version.
  2. 2 · completeUse the base model to continue an initial text prompt.
  3. 3 · tuneFurther fine-tune the base version on instructions and conversational data.
  4. 4 · instructUse the instruction-tuned variant to respond to instructions or requests.

Base identifies the pretrained model before further tuning.

4 · Where it's used
WhoWhat they askWhat it works with
Model developer“Which pretrained model should receive further tuning?”Base model lineage
Inference engineer“Is this variant intended for completion or instruction following?”Variant type
Adapter user“Which original model must be loaded with this adapter?”Adapter base model
5 · What it solves, and what it doesn't
solves
  • It names the pretrained model before instruction or conversational fine-tuning.
  • It can be used directly for text completion.
  • Using a parameter-efficient adapter also requires loading its base model.
doesn't solve
  • Base models are not ideal for tasks that require following instructions.
  • An adapter does not replace the base model it was trained against.
6 · Go deeper

Sources used

This explainer is written in original language. The links below support its factual claims.

  1. docsLLM prompting guide, Hugging Face · read 28 Sept 2026
  2. docsRun Gemma content generation and inferences, Google AI for Developers · read 28 Sept 2026
  3. officialGemma model card, Google AI for Developers · read 28 Sept 2026
  4. paperLlama 2 - Open Foundation and Fine-Tuned Chat Models, Touvron et al. · read 28 Sept 2026
  5. docsUsing PEFT at Hugging Face, Hugging Face · read 28 Sept 2026